AI
AI / LLM engineer
Full-time or contract · Remote · worldwide
- Posted
- October 7, 2026
- Apply by
- October 14, 2026
- Compensation
- Up to $30,000 USD per year (experience and region)
Build copilots, RAG pipelines, and evaluation loops that stay grounded in client data — with guardrails, cost control, and human review where it matters.
About this role
You will turn LLM ideas into production features clients can trust: retrieval that stays on their data, evaluation that catches regressions, and UX that keeps a human in the loop for high-stakes actions. We care more about shipping safe systems than flashy demos.
What success looks like
- Ships an LLM feature with evals, logging, and cost awareness
- Documents failure modes and safe defaults for client operators
- Improves grounding and retrieval quality with measurable checks
- Partners with product engineers on clear human-review paths
Responsibilities
- Design and ship RAG, copilots, and workflow automation in production products
- Build evaluation sets, prompt versioning, and quality monitoring
- Enforce permissions, logging, and cost controls around model usage
- Partner with product engineers on UX that keeps humans in the loop
- Document failure modes and safe defaults for client teams
Requirements
- Hands-on experience shipping LLM features beyond demos
- Comfort with Python and/or TypeScript service work
- Understanding of retrieval, embeddings, and evaluation basics
- Clear written English for async collaboration
Nice to have
- LangChain, LlamaIndex, or similar orchestration experience
- Vector database familiarity (pgvector, etc.)
- Arabic reading/writing is a plus
How to apply
Use Match CV & apply on this role: we score your CV against the opening, show you the gaps, and submit your application with your PDF and match summary. Prefer to write yourself? Use the email link below. We typically reply within a few business days.
Or write directly to careers@mechabits.com